American Institute of Physics

Peering inside the machine learning black box for fusion experiments

Statistical insights into machine learning analysis can help researchers evaluate model performance and may even provide new physical understanding.

Survival training in a safe space—how staged risk helps young predators learn dangerous prey

Adaptation is essential for survival. Across species, it occurs over many generations through evolution and natural selection ...

Microsoft's new AI training method eliminates bloated system prompts without sacrificing model performance

Microsoft researchers have developed On-Policy Context Distillation (OPCD), a training method that permanently embeds ...

Are climate models detecting monsoon changes a decade too early? 'Super-simulations' say yes

Changes in rainfall within global monsoon regions affect the livelihoods of billions. For years, climate models have ...

Xue Li Enhancing Energy Storage Systems Through Battery State-of-Health Estimation and Intelligent Control Strategies

A dual-model battery health assessment framework analyzes real-world voltage data from retired EV batteries in grid storage. Using incremental ...
Scientific Research Publishing

A Hybrid Machine Learning Framework for Early Diabetes Prediction in Sierra Leone Using Feature Selection and Soft-Voting Ensemble ()

A Hybrid Machine Learning Framework for Early Diabetes Prediction in Sierra Leone Using Feature Selection and Soft-Voting Ensemble ...
GitHub

mohansree14/Bayesian-Deep-Learning-for-Probabilistic-Financial-Forecasting

This project implements state-of-the-art deep learning models for financial time series forecasting with a focus on uncertainty quantification. The system provides not just point predictions, but ...
Scientific Research Publishing

Kevin, M.K.P. and Murphy, P. (2022) Probabilistic Machine Learning: An Introduction. The MIT Press, Cambridge.

ABSTRACT: Blasting is a cost-effective technique to break hard rock volumes by using explosives in the mining and civil engineering realms. Moreover, although blasting is a designed process and plays ...
IEEE

Probabilistic Deep Learning Model for Time Series Analysis

Abstract: In this paper, we propose a novel approach for probabilistic time series modeling using deep learning, capitalizing on the flexibility of Functional Neural Networks (FNNs) and the benefits ...
IEEE

Deep Residual Learning of a Probabilistic’ Partial Least Squares Model for Predictive Data Analytics

Abstract: Recently, probabilistic latent variable models have played an important role in data analytics in various industrial application scenarios, such as process monitoring, fault diagnosis, and ...